Skip to main content

Table 3 Top 10 important genes from SNV-based and gene-based models

From: Machine learning analysis of exome trios to contrast the genomic architecture of autism and schizophrenia

SNV-based approach (SNV rsID)

Gene-based approach

SARM1 (rs71373646)

SARM1

QRICH2 (rs6501878)

QRICH2

AKAP1 (rs34535433)

PRPF31

PCLO (rs77721383)

SEC24D

TSPO2 (rs147405274)

SCN4A

ABCC3 (rs11568605)

CACNA1S

KIF13A (rs41267712)

CDSN

FAN1 (rs150393409)

HERC2

CCDC155 (rs201671744)

MUC16

PRPF31 (rs199870856)

PCLO

  1. Boosted regression trees models were trained to separate SCZ and ASD probands based on the population-structure-adjusted SNV-based and gene-based datasets. The 10 most important genes from the gene-based model, but also from the SNV-based approach (including the actual SNV in parenthesis), are shown in this table. The table is ordered from most to least importance